Difference between revisions of "Gneuralnetwork"
(resources) |
m (Text replacement - "|Documentation note='''Selection from the [https://shop.fsf.org/ FSF shop]''' [https://shop.fsf.org/books/free-freedom-20-richard-stallman Free as in Freedom 2.0, by Richard Stallman] [https://shop.fsf.org/books-docs/introduction-...) |
||
| (2 intermediate revisions by one other user not shown) | |||
| Line 1: | Line 1: | ||
{{Entry | {{Entry | ||
|Name=GNU Gneural Network | |Name=GNU Gneural Network | ||
| − | |Short description= | + | |Short description=Implement a programmable neural network. |
|Full description=Gneural Network is the GNU package which implements a programmable neural network. The current version, 0.9.1, has the following features: | |Full description=Gneural Network is the GNU package which implements a programmable neural network. The current version, 0.9.1, has the following features: | ||
| Line 16: | Line 16: | ||
|Is High Priority Project=No | |Is High Priority Project=No | ||
|VCS checkout command=git clone git://git.savannah.gnu.org/gneuralnetwork.git | |VCS checkout command=git clone git://git.savannah.gnu.org/gneuralnetwork.git | ||
| + | |||
|Decommissioned or Obsolete=No | |Decommissioned or Obsolete=No | ||
| − | |Donate=https://my.fsf.org/donate | + | |Donate=https://my.fsf.org/donate/ |
| + | |Related projects=gnustandards | ||
|Version identifier=0.9.1 | |Version identifier=0.9.1 | ||
|Version date=2016/05/03 | |Version date=2016/05/03 | ||
|Version status=developmental | |Version status=developmental | ||
| − | |Version download= | + | |Version download=https://cvs.savannah.gnu.org/viewvc/*checkout*/gneuralnetwork/gneural_network-0.9.1.tar.gz?revision=1.1&root=gneuralnetwork |
|Last review by=Bendikker | |Last review by=Bendikker | ||
| − | |Last review date= | + | |Last review date=2019/01/03 |
|Submitted by=Quark | |Submitted by=Quark | ||
|Submitted date=2016/09/28 | |Submitted date=2016/09/28 | ||
|User level=advanced | |User level=advanced | ||
|Component programs=gneural | |Component programs=gneural | ||
| + | |Paid support=https://www.fsf.org/resources/service/ | ||
|Accepts cryptocurrency donations=Yes | |Accepts cryptocurrency donations=Yes | ||
|Test entry=No | |Test entry=No | ||
| Line 56: | Line 59: | ||
{{Resource | {{Resource | ||
|Resource audience=Savannah (Ref) | |Resource audience=Savannah (Ref) | ||
| − | |Resource URL=https://savannah.gnu.org/projects/gneuralnetwork | + | |Resource URL=https://savannah.gnu.org/projects/gneuralnetwork/ |
}} | }} | ||
{{Resource | {{Resource | ||
|Resource kind=VCS Repository Webview | |Resource kind=VCS Repository Webview | ||
| − | |Resource URL=https://git.savannah.gnu.org/cgit/gneuralnetwork.git | + | |Resource URL=https://git.savannah.gnu.org/cgit/gneuralnetwork.git/ |
}} | }} | ||
{{Resource | {{Resource | ||
|Resource kind=Mailing List | |Resource kind=Mailing List | ||
| − | |Resource URL=https://lists.gnu.org/mailman/listinfo/gneuralnetwork | + | |Resource URL=https://lists.gnu.org/mailman/listinfo/gneuralnetwork/ |
}} | }} | ||
{{Resource | {{Resource | ||
|Resource kind=Mailing List | |Resource kind=Mailing List | ||
| − | |Resource URL=https://lists.gnu.org/mailman/listinfo/gnu-system-discuss | + | |Resource URL=https://lists.gnu.org/mailman/listinfo/gnu-system-discuss/ |
}} | }} | ||
{{Resource | {{Resource | ||
|Resource kind=Download | |Resource kind=Download | ||
| − | |Resource URL=https://cvs.savannah.gnu.org/viewvc/gneuralnetwork | + | |Resource URL=https://cvs.savannah.gnu.org/viewvc/gneuralnetwork/ |
| + | }} | ||
| + | {{Resource | ||
| + | |Resource kind=General | ||
| + | |Resource URL=https://savannah.gnu.org/people/ | ||
}} | }} | ||
{{Software category | {{Software category | ||
Latest revision as of 13:41, 4 December 2020
GNU Gneural Network
https://www.gnu.org/software/gneuralnetwork/
Implement a programmable neural network.
Gneural Network is the GNU package which implements a programmable neural network. The current version, 0.9.1, has the following features:
- A scripting language is available which allows users to define their own neural network without having to know anything about coding.
- Advanced programmers can use the methods/routines inside the code for their own purposes.
- When defining the neurons of a network, it is possible to choose among various discriminant and activation functions, etc.
- Different methods to train a neural network are available, such as genetic algorithms, multi-scale Monte Carlo optimizers, simulated annealing, and others.
- Several training methods can run in parallel on clusters.
- Neural networks can be saved once trained for later use.
- The code is truly cross platform since it is entirely developed in C and does not depend on any external library.
The network can now learn tasks defined by the user. An example of script defining a simple network which fits a curve is given. We plan to deliver more advanced features very soon. In particular, we are already spending efforts to implement recurrent networks. We also plan to implement learning reinforcement techniques and apply Gneural Network for deep learning applications. We will release the data along with the trained network.
Licensing
License
Verified by
Verified on
Notes
Leaders and contributors
| Contact(s) | Role |
|---|---|
| Ray Dillinger | contributor |
| Jean Michel Sellier | Maintainer |
| Aljosha Papsch | contributor |
Resources and communication
Software prerequisites
Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.3 or any later version published by the Free Software Foundation; with no Invariant Sections, no Front-Cover Texts, and no Back-Cover Texts. A copy of the license is included in the page “GNU Free Documentation License”.
The copyright and license notices on this page only apply to the text on this page. Any software or copyright-licenses or other similar notices described in this text has its own copyright notice and license, which can usually be found in the distribution or license text itself.